Imperial College London


Faculty of MedicineDepartment of Surgery & Cancer

Professor of Critical Care



+44 (0)20 3313 4521stephen.brett Website




Hammersmith House 570Hammersmith HospitalHammersmith Campus






BibTex format

author = {Meiring, C and Dixit, A and Harris, S and MacCallum, NS and Brealey, DA and Watkinson, PJ and Jones, A and Ashworth, S and Beale, R and Brett, SJ and Singer, S and Ercole, A},
doi = {10.1371/journal.pone.0206862},
journal = {PLoS ONE},
title = {Optimal intensive care outcome prediction over time using machine learning},
url = {},
volume = {13},
year = {2018}

RIS format (EndNote, RefMan)

AB - BackgroundPrognostication is an essential tool for risk adjustment and decision making in the intensive care unit (ICU). Research into prognostication in ICU has so far been limited to data from admission or the first 24 hours. Most ICU admissions last longer than this, decisions are made throughout an admission, and some admissions are explicitly intended as time-limited prognostic trials. Despite this, temporal changes in prognostic ability during ICU admission has received little attention to date. Current predictive models, in the form of prognostic clinical tools, are typically derived from linear models and do not explicitly handle incremental information from trends. Machine learning (ML) allows predictive models to be developed which use non-linear predictors and complex interactions between variables, thus allowing incorporation of trends in measured variables over time; this has made it possible to investigate prognosis throughout an admission.Methods and findingsThis study uses ML to assess the predictability of ICU mortality as a function of time. Logistic regression against physiological data alone outperformed APACHE-II and demonstrated several important interactions including between lactate & noradrenaline dose, between lactate & MAP, and between age & MAP consistent with the current sepsis definitions. ML models consistently outperformed logistic regression with Deep Learning giving the best results. Predictive power was maximal on the second day and was further improved by incorporating trend data. Using a limited range of physiological and demographic variables, the best machine learning model on the first day showed an area under the receiver-operator characteristic curve (AUC) of 0.883 (σ = 0.008), compared to 0.846 (σ = 0.010) for a logistic regression from the same predictors and 0.836 (σ = 0.007) for a logistic regression based on the APACHE-II score. Adding information gathered on the second day of admission imp
AU - Meiring,C
AU - Dixit,A
AU - Harris,S
AU - MacCallum,NS
AU - Brealey,DA
AU - Watkinson,PJ
AU - Jones,A
AU - Ashworth,S
AU - Beale,R
AU - Brett,SJ
AU - Singer,S
AU - Ercole,A
DO - 10.1371/journal.pone.0206862
PY - 2018///
SN - 1932-6203
TI - Optimal intensive care outcome prediction over time using machine learning
UR -
UR -
VL - 13
ER -